mlsanityData to 7 Oct 2026

aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio

arXiv 2409.03377 ↗First posted 5 Sep 2024cs.SD cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We present aTENNuate, a simple deep state-space autoencoder configured for efficient online raw speech enhancement in an end-to-end fashion. The network's performance is primarily evaluated on raw speech denoising, with additional assessments on tasks such as super-resolution and de-quantization. We benchmark aTENNuate on the VoiceBank + DEMAND and the Microsoft DNS1 synthetic test sets. The network outperforms previous real-time denoising models in terms of PESQ score, parameter count, MACs, and latency. Even as a raw waveform processing model, the model maintains high fidelity to the clean signal with minimal audible artifacts. In addition, the model remains performant even when the noisy input is compressed down to 4000Hz and 4 bits, suggesting general speech enhancement capabilities in low-resource environments. Try it out by pip install attenuate

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 34 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

28 of 34 references.

References · 28

  1. 2015Fast R-CNNcited by 2,930
  2. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  3. 2022Simplified State Space Layers for Sequence Modelingcited by 776
  4. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 418
  5. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  6. 2022It's Raw! Audio Generation with State-Space Modelscited by 171
  7. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  8. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 133
  9. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 128
  10. 2019Phase-aware Speech Enhancement with Deep Complex U-Netcited by 73
  11. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 61
  12. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 58
16 more
  1. 2017A Wavenet for Speech Denoisingcited by 47
  2. 2023SELM: Speech Enhancement Using Discrete Tokens and Language Modelscited by 36
  3. 2017A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancementcited by 34
  4. 2018Speech Denoising with Deep Feature Lossescited by 26
  5. 2023DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancementcited by 25
  6. 2022FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancementcited by 24
  7. 2020A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speechcited by 23
  8. 2023Spiking Structured State Space Model for Monaural Speech Enhancementcited by 23
  9. 2021Speech Denoising Without Clean Training Data: A Noise2Noise Approachcited by 17
  10. 2024A Lightweight Spatiotemporal Network for Online Eye Tracking with Event Cameracited by 14
  11. 2022Speech Denoising in the Waveform Domain with Self-Attentioncited by 13
  12. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Modelscited by 9
  13. 2020A Review of Multi-Objective Deep Learning Speech Denoising Methodscited by 6
  14. 2018Convolutional Neural Networks to Enhance Coded Speechcited by 4
  15. 2020Speech Enhancement based on Denoising Autoencoder with Multi-branched Encoderscited by 4
  16. 2024PLEIADES: Building Temporal Kernels with Orthogonal Polynomialscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Modulating State Space Model with SlowFast Framework for Compute-Efficient Ultra Low-Latency Speech Enhancement
  2. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training
  3. 2026Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancement
  4. 2025Model as Loss: A Self-Consistent Training Paradigm
  5. 2026RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation
  6. 2024SICRN: Advancing Speech Enhancement through State Space Model and Inplace Convolution Techniques
  7. 2026Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codec
  8. 2025MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow